# Information Retrieval on Medical Retrieval

Source: [Information Retrieval on Medical Retrieval](<https://www.sota2.com/research/sota/information-retrieval-on-medical-retrieval>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:50:25.678Z

Evaluation of Information Retrieval performance on the Medical Retrieval dataset, measured using MRR and Recall.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Information Retrieval |
| Dataset (including any stated split) | Medical Retrieval |
| Metric | MRR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [MRR](<https://www.sota2.com/research/sota/information-retrieval-on-medical-retrieval.md?metric=MRR>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/information-retrieval-on-medical-retrieval.md?metric=Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | MRR | Result date | Report paper |
| --- | --- | --- | --- |
| BGE(326M) | 55.04 | Not recorded | 68fa73e21e209131cea5ea7a |
| D2LLM(7B) | 49.91 | Not recorded | 68fa73e21e209131cea5ea7a |
| LLARA(7B) | 46.12 | Not recorded | 68fa73e21e209131cea5ea7a |
| BGE-ft(326M) | 45.61 | Not recorded | 68fa73e21e209131cea5ea7a |
| Udever(7B) | 43.46 | Not recorded | 68fa73e21e209131cea5ea7a |
| SGPT(7B) | 32.66 | Not recorded | 68fa73e21e209131cea5ea7a |
| RocketQAv2(326M) | 29.79 | Not recorded | 68fa73e21e209131cea5ea7a |
| LLM-be(7B) | 4.62 | Not recorded | 68fa73e21e209131cea5ea7a |

### BGE(326M)

MRR: 55.04. Result ID: 6993106f3a6c314849137255.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73e21e209131cea5ea7a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74e31e209131cea64745.md>)

Recorded evaluation configuration: {"#Data":"100M","#Param.":"326M"}. This record does not assert independent reproduction.

### D2LLM(7B)

MRR: 49.91. Result ID: 6993106f3a6c314849137254.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73e21e209131cea5ea7a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73e21e209131cea5ea7a.md>)

[Implementation](<https://github.com/codefuse-ai/D2LLM>)

Recorded evaluation configuration: {"#Data":"0.9M","#Param.":"7B"}. This record does not assert independent reproduction.

### LLARA(7B)

MRR: 46.12. Result ID: 6993106f3a6c314849137253.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73e21e209131cea5ea7a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ae1e209131cea52833.md>)

[Implementation](<https://github.com/FlagOpen/FlagEmbedding>)

Recorded evaluation configuration: {"#Data":"0.9M","#Param.":"7B"}. This record does not assert independent reproduction.

### BGE-ft(326M)

MRR: 45.61. Result ID: 6993106f3a6c31484913724f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73e21e209131cea5ea7a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74e31e209131cea64745.md>)

Recorded evaluation configuration: {"#Data":"0.9M","#Param.":"326M"}. This record does not assert independent reproduction.

### Udever(7B)

MRR: 43.46. Result ID: 6993106f3a6c314849137252.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73e21e209131cea5ea7a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78ba1e209131cea7a177.md>)

Recorded evaluation configuration: {"#Data":"0.9M","#Param.":"7B"}. This record does not assert independent reproduction.

### SGPT(7B)

MRR: 32.66. Result ID: 6993106f3a6c314849137251.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73e21e209131cea5ea7a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d341e209131cea3860b.md>)

[Implementation](<https://github.com/Muennighoff/sgpt>)

Recorded evaluation configuration: {"#Data":"0.9M","#Param.":"7B"}. This record does not assert independent reproduction.

### RocketQAv2(326M)

MRR: 29.79. Result ID: 6993106f3a6c314849137250.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73e21e209131cea5ea7a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f281e209131cea4425f.md>)

Recorded evaluation configuration: {"#Data":"0.9M","#Param.":"326M"}. This record does not assert independent reproduction.

### LLM-be(7B)

MRR: 4.62. Result ID: 6993106f3a6c314849137256.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73e21e209131cea5ea7a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d41e209131cea4d774.md>)

[Implementation](<https://github.com/QwenLM/Qwen-VL>)

Recorded evaluation configuration: {"#Data":"N/A","#Param.":"7B"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
